Google DeepMind's recent AI Co-Mathematician agent, leveraging Gemini 3.1 Pro as its base large language model, achieved a breakthrough 48% on FrontierMath's challenging Tier 4—doubling the underlying model's 19% score—demonstrating agentic scaffolding's potential for advanced mathematical reasoning, as announced May 13. However, standalone Gemini models trail OpenAI's GPT-5.5 Pro, which leads the overall FrontierMath leaderboard at 52.4%, reflecting OpenAI's edge in raw AI capabilities on this benchmark of unsolved research problems. Trader consensus hinges on Google I/O next week (May 19-20), where a new Gemini iteration or reasoning upgrades like Deep Think could close the gap before the June 30 deadline, amid rapid benchmark saturation.
Експериментальне резюме, згенероване ШІ з посиланням на дані Polymarket. Це не торгова порада і не впливає на вирішення цього ринку. · ОновленоGoogle Gemini score on FrontierMath Benchmark by June 30?
Google Gemini score on FrontierMath Benchmark by June 30?
$136,324 Обс.
40%+
86%
45%+
68%
50%+
62%
60%+
54%
$136,324 Обс.
40%+
86%
45%+
68%
50%+
62%
60%+
54%
This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
Ринок відкрито: Feb 6, 2026, 6:03 PM ET
Resolver
0x65070BE91...This market will resolve according to the Epoch AI’s Frontier Math benchmarking leaderboard (https://epoch.ai/frontiermath) for Tier 1-3. Studies which are not included in the leaderboard (e.g. https://x.com/EpochAIResearch/status/1945905796904005720) will not be considered.
The primary resolution source will be information from EpochAI; however, a consensus of credible reporting may also be used.
Resolver
0x65070BE91...Google DeepMind's recent AI Co-Mathematician agent, leveraging Gemini 3.1 Pro as its base large language model, achieved a breakthrough 48% on FrontierMath's challenging Tier 4—doubling the underlying model's 19% score—demonstrating agentic scaffolding's potential for advanced mathematical reasoning, as announced May 13. However, standalone Gemini models trail OpenAI's GPT-5.5 Pro, which leads the overall FrontierMath leaderboard at 52.4%, reflecting OpenAI's edge in raw AI capabilities on this benchmark of unsolved research problems. Trader consensus hinges on Google I/O next week (May 19-20), where a new Gemini iteration or reasoning upgrades like Deep Think could close the gap before the June 30 deadline, amid rapid benchmark saturation.
Експериментальне резюме, згенероване ШІ з посиланням на дані Polymarket. Це не торгова порада і не впливає на вирішення цього ринку. · Оновлено
Обережно з зовнішніми посиланнями.
Обережно з зовнішніми посиланнями.
Часті запитання